<strong>Background:</strong> <span style="font-family:;" "=""><span style="font-family:Verdana;">In patients with breast cancer after Neoadjuvant Chemotherapy...<strong>Background:</strong> <span style="font-family:;" "=""><span style="font-family:Verdana;">In patients with breast cancer after Neoadjuvant Chemotherapy (NAC), pathological Complete Response (pCR) was associated with better </span><span style="font-family:Verdana;">long-term outcome</span></span><span style="font-family:Verdana;">s</span><span style="font-family:Verdana;">. We here attempted to predict pCR using machine</span><span style="font-family:;" "=""><span style="font-family:Verdana;"> learning. </span><b><span style="font-family:Verdana;">Patients and Methods:</span></b><span style="font-family:Verdana;"> From 2008 to 2017, 1308 breast cancer patients underwent NAC before surgery, of whom 377 patients underwent Cancer</span></span><span style="font-family:;" "=""> </span><span style="font-family:;" "=""><span style="font-family:Verdana;">SCAN</span><sup><span style="font-family:Verdana;">TM</span></sup><span style="font-family:Verdana;"> for gene data. Of 377, 238 were analyzed here, with 139 excluded due to incomplete medical data. </span><b><span style="font-family:Verdana;">Results: </span></b><span style="font-family:Verdana;">The pCR (-</span></span><span style="font-family:;" "=""><span><span style="font-family:Verdana;">) vs. (+) group had 200 vs. 38 patients. In our predictive model with gene data, the Area Under the </span><span style="font-family:Verdana;">Curve (AUC) of the Receiver Operating Characteristic (ROC) curve was</span><span style="font-family:Verdana;"> 0.909 and accuracy was 0.875. In another model without gene data, the AUC of ROC curve was 0.743 and accuracy was 0.800. We also conducted internal validation with 72 patients undergoing NAC and Cancer</span></span></span><span style="font-family:;" "=""> </span><span style="font-family:;" "=""><span style="font-family:Verdana;">SCAN</span><sup><span style="font-family:Verdana;">TM</span></sup><span style="font-family:Verdana;"> during July 2017 and April 2018. When we applied a 0.4 threshold value, accuracy was </span><span style="font-family:Verdana;">0.806 and 0.778 in </span></span><span style="font-family:Verdana;">the </span><span style="font-family:Verdana;">predictive model with vs. without gene profiles, </span><span style="font-family:;" "=""><span style="font-family:Verdana;">respec</span><span><span style="font-family:Verdana;">tively. </span><b><span style="font-family:Verdana;">Conclusion:</span></b><span style="font-family:Verdana;"> The present predictive model may be a useful an</span></span><span style="font-family:Verdana;">d</span><span style="font-family:Verdana;"> easy-to-access tool for pCR-prediction in breast cancer patients treated with NAC.</span></span>展开更多
文摘<strong>Background:</strong> <span style="font-family:;" "=""><span style="font-family:Verdana;">In patients with breast cancer after Neoadjuvant Chemotherapy (NAC), pathological Complete Response (pCR) was associated with better </span><span style="font-family:Verdana;">long-term outcome</span></span><span style="font-family:Verdana;">s</span><span style="font-family:Verdana;">. We here attempted to predict pCR using machine</span><span style="font-family:;" "=""><span style="font-family:Verdana;"> learning. </span><b><span style="font-family:Verdana;">Patients and Methods:</span></b><span style="font-family:Verdana;"> From 2008 to 2017, 1308 breast cancer patients underwent NAC before surgery, of whom 377 patients underwent Cancer</span></span><span style="font-family:;" "=""> </span><span style="font-family:;" "=""><span style="font-family:Verdana;">SCAN</span><sup><span style="font-family:Verdana;">TM</span></sup><span style="font-family:Verdana;"> for gene data. Of 377, 238 were analyzed here, with 139 excluded due to incomplete medical data. </span><b><span style="font-family:Verdana;">Results: </span></b><span style="font-family:Verdana;">The pCR (-</span></span><span style="font-family:;" "=""><span><span style="font-family:Verdana;">) vs. (+) group had 200 vs. 38 patients. In our predictive model with gene data, the Area Under the </span><span style="font-family:Verdana;">Curve (AUC) of the Receiver Operating Characteristic (ROC) curve was</span><span style="font-family:Verdana;"> 0.909 and accuracy was 0.875. In another model without gene data, the AUC of ROC curve was 0.743 and accuracy was 0.800. We also conducted internal validation with 72 patients undergoing NAC and Cancer</span></span></span><span style="font-family:;" "=""> </span><span style="font-family:;" "=""><span style="font-family:Verdana;">SCAN</span><sup><span style="font-family:Verdana;">TM</span></sup><span style="font-family:Verdana;"> during July 2017 and April 2018. When we applied a 0.4 threshold value, accuracy was </span><span style="font-family:Verdana;">0.806 and 0.778 in </span></span><span style="font-family:Verdana;">the </span><span style="font-family:Verdana;">predictive model with vs. without gene profiles, </span><span style="font-family:;" "=""><span style="font-family:Verdana;">respec</span><span><span style="font-family:Verdana;">tively. </span><b><span style="font-family:Verdana;">Conclusion:</span></b><span style="font-family:Verdana;"> The present predictive model may be a useful an</span></span><span style="font-family:Verdana;">d</span><span style="font-family:Verdana;"> easy-to-access tool for pCR-prediction in breast cancer patients treated with NAC.</span></span>
